1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
|
from nose.tools import istest, assert_equal
from mammoth import documents, document_matchers
from mammoth.styles.parser.document_matcher_parser import parse_document_matcher
from mammoth.styles.parser.errors import LineParseError
from mammoth.styles.parser.tokeniser import tokenise
from mammoth.styles.parser.token_iterator import TokenIterator
from ...testing import assert_raises
@istest
def unrecognised_document_element_raises_error():
error = assert_raises(LineParseError, lambda: read_document_matcher("x"))
assert_equal("Unrecognised document element: x", str(error))
@istest
def reads_plain_paragraph():
assert_equal(
document_matchers.paragraph(),
read_document_matcher("p")
)
@istest
def reads_paragraph_with_style_id():
assert_equal(
document_matchers.paragraph(style_id="Heading1"),
read_document_matcher("p.Heading1")
)
@istest
def reads_paragraph_with_exact_style_name():
assert_equal(
document_matchers.paragraph(style_name=document_matchers.equal_to("Heading 1")),
read_document_matcher("p[style-name='Heading 1']")
)
@istest
def reads_paragraph_with_style_name_prefix():
assert_equal(
document_matchers.paragraph(style_name=document_matchers.starts_with("Heading")),
read_document_matcher("p[style-name^='Heading']")
)
@istest
def unrecognised_string_matcher_raises_error():
error = assert_raises(LineParseError, lambda: read_document_matcher("p[style-name*='Heading']"))
assert_equal("Unrecognised string matcher: *", str(error))
@istest
def reads_paragraph_ordered_list():
assert_equal(
document_matchers.paragraph(numbering=documents.numbering_level(1, is_ordered=True)),
read_document_matcher("p:ordered-list(2)")
)
@istest
def reads_paragraph_unordered_list():
assert_equal(
document_matchers.paragraph(numbering=documents.numbering_level(1, is_ordered=False)),
read_document_matcher("p:unordered-list(2)")
)
@istest
def unrecognised_list_type_raises_error():
error = assert_raises(LineParseError, lambda: read_document_matcher("p:blah"))
assert_equal("Unrecognised list type: blah", str(error))
@istest
def reads_plain_run():
assert_equal(
document_matchers.run(),
read_document_matcher("r")
)
@istest
def reads_run_with_style_id():
assert_equal(
document_matchers.run(style_id="Emphasis"),
read_document_matcher("r.Emphasis")
)
@istest
def reads_run_with_style_name():
assert_equal(
document_matchers.run(style_name=document_matchers.equal_to("Emphasis")),
read_document_matcher("r[style-name='Emphasis']")
)
@istest
def reads_bold():
assert_equal(
document_matchers.bold,
read_document_matcher("b")
)
@istest
def reads_italic():
assert_equal(
document_matchers.italic,
read_document_matcher("i")
)
@istest
def reads_underline():
assert_equal(
document_matchers.underline,
read_document_matcher("u")
)
@istest
def reads_strikethrough():
assert_equal(
document_matchers.strikethrough,
read_document_matcher("strike")
)
@istest
def reads_comment_reference():
assert_equal(
document_matchers.comment_reference,
read_document_matcher("comment-reference")
)
@istest
def reads_line_breaks():
assert_equal(
document_matchers.line_break,
read_document_matcher("br[type='line']"),
)
@istest
def reads_page_breaks():
assert_equal(
document_matchers.page_break,
read_document_matcher("br[type='page']"),
)
@istest
def reads_column_breaks():
assert_equal(
document_matchers.column_break,
read_document_matcher("br[type='column']"),
)
@istest
def unrecognised_break_type_raises_error():
error = assert_raises(LineParseError, lambda: read_document_matcher("br[type='unknownBreakType']"))
assert_equal("Unrecognised break type: unknownBreakType", str(error))
def read_document_matcher(string):
return parse_document_matcher(TokenIterator(tokenise(string)))
|
